Large Language Models are increasingly combined with knowledge graphs to support multi-hop factual reasoning. A classical strategy for handling complex questions in such settings is question decomposition, where a question is broken into simpler subquestions to guide retrieval. While decomposition can improve relevance, its impact on the structure and connectivity of the retrieved information, as well as the implications for downstream reasoning, remain unclear. In this work, we present a diagnostic study of the effects of question decomposition on knowledge graph retrieval. We use a simple parametric interpolation between retrieval guided by the original question and its subquestions, allowing us to vary retrieval focus in a controlled manner. By softly anchoring subquestion-level retrieval to the original question, we allow structural properties of the retrieved subgraph to change naturally, without post-hoc enforcement of connectivity. Across different multi-hop QA benchmarks, we observe a consistent structure-content trade-off: subquestion-focused retrieval improves content precision but fragments the retrieved graph, whereas question-focused retrieval preserves structural coherence at the cost of relevance. Downstream QA performance peaks at intermediate settings, where sufficient connectivity emerges while maintaining high relevance. These results highlight the importance of jointly considering content and structure when designing retrieval strategies for reasoning over structured knowledge.

Political biases encoded by LLMs might have detrimental effects on downstream applications. Existing bias analysis methods rely on small-size intermediate tasks (questionnaire answering or political content generation) and rely on the LLMs themselves for analysis, thus propagating bias. We propose a new approach leveraging the observation that LLM sentiment predictions vary with the target entity in the same sentence. We define an entropy-based inconsistency metric to encode this prediction variability. We insert 1319 demographically and politically diverse politician names in 450 political sentences and predict target-oriented sentiment using seven models in six widely spoken languages. We observe inconsistencies in all tested combinations and aggregate them in a statistically robust analysis at different granularity levels. We observe positive and negative bias toward left and far-right politicians and positive correlations between politicians with similar alignment. Bias intensity is higher for Western languages than for others. Larger models exhibit stronger and more consistent biases and reduce discrepancies between similar languages. We partially mitigate LLM unreliability in target-oriented sentiment classification (TSC) by replacing politician names with fictional but plausible counterparts. The complete code, the data, and all analyses will be made public to enable reproducibility.

Target-dependent sentiment classification (TSC) enables a fine-grained automatic analysis of sentiments expressed in texts. Sentiment expression varies depending on the domain, and it is necessary to create domain-specific datasets. While socially important, TSC in the news domain remains relatively understudied. We introduce MAD-TSC, a new dataset which differs substantially from existing resources. First, it includes aligned examples in eight languages to facilitate a comparison of performance for individual languages, and a direct comparison of human and machine translation. Second, the dataset is sampled from a diversified parallel news corpus, and is diversified in terms of news sources and geographic spread of entities. Finally, MAD-TSC is more challenging than existing datasets because its examples are more complex. We exemplify the use of MAD-TSC with comprehensive monolingual and multilingual experiments. The latter show that machine translations can successfully replace manual ones, and that performance for all included languages can match that of English by automatically translating test examples.

Online news consumption plays an important role in shaping the political opinions of citizens. The news is often served by recommendation algorithms, which adapt content to users’ preferences. Such algorithms can lead to political polarization as the societal effects of the recommended content and recommendation design are disregarded. We posit that biases appear, at least in part, due to a weak entanglement between natural language processing and recommender systems, both processes yet at work in the diffusion and personalization of online information. We assume that both diversity and acceptability of recommended content would benefit from such a synergy. We discuss the limitations of current approaches as well as promising leads of opinion-mining integration for the political news recommendation process.